/ 100

1 day ago

glama

mcp-llm-router

An MCP server that routes LLM requests across multiple providers and orchestrates other MCP servers, with a focus on local privacy for embeddings and memory.

→ groxaxo/mcp-llm-router · listed on glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

🔐

You'll be asked for 2 credentials: LLM_API_KEY, DEEPSEEK_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configOPENAI_BASE_URL

configOPENROUTER_BASE_URL

configDEEPINFRA_BASE_URL

configANTHROPIC_BASE_URL

configDEEPSEEK_BASE_URL

configMCP_JUDGE_DATABASE_URL— export ="sqlite:///./.mcp-llm-router/judge_history.db"

🔐 secretLLM_API_KEY— Note: the demo skips request_plan_approval because it requires user elicitation. Ensure DEEPSEEK_API_KEY (or ) is set and Ollama is running for embeddings.

configLLM_MODEL_NAME

configLLM_BASE_URL

🔐 secretDEEPSEEK_API_KEY— "": "your-deepseek-key",

configMODEL

configMCP_JUDGE_ENABLE_TASKS

configEMBEDDINGS_BASE_URL— "": "http://localhost:11434",

configEMBEDDINGS_MODEL— export ="nomic-embed-text"

configEMBEDDINGS_PROVIDER— "": "ollama",

configEMBEDDINGS_PATH— export ="/api/embed"

configRERANK_BASE_URL— export ="https://api.openai.com/v1"

configRERANK_MODEL— export ="tomaarsen/Qwen3-Reranker-0.6B-seq-cls" # Default model

configRERANK_PROVIDER— export ="local"

configRERANK_PATH— export ="/chat/completions"

configRERANK_MODE— export ="local"

configEMBEDDINGS_API_KEY_ENV— No needed for local Ollama!

configRERANK_API_KEY_ENV— export ="OPENAI_API_KEY"

configMCP_ROUTER_MEMORY_DB— export ="./.mcp-llm-router/memory.db"

configROUTER_BRAIN_MODEL— "": "deepseek-reasoner",

configROUTER_BRAIN_BASE_URL— "": "https://openrouter.ai/api/v1",

configROUTER_BRAIN_API_KEY_ENV— "": "DEEPSEEK_API_KEY",

configROUTER_BRAIN_PROVIDER— "": "deepseek",

configROUTER_BRAIN_MAX_TOKENS— export ="4000"

configROUTER_BRAIN_TEMPERATURE— export ="0.2"

configROUTER_BRAIN_SYSTEM_PROMPT

configROUTER_BRAIN_REASONING_EFFORT

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/groxaxo-mcp-llm-router-32qptg)](https://m8ven.ai/mcp/groxaxo-mcp-llm-router-32qptg)

commit: b977ab42d9d00f05c18c1341c45bfe99b79e85f0

code hash: e8c60d173d34c97b556187c911a95c5d9b4767770fd850dc976127ac3c68e1e2

verified: 6/23/2026, 10:34:38 AM

view raw JSON →